JP7097191B2 - Estimator and estimation method - Google Patents

Description

The present invention relates to an estimation device for estimating the position of a force point to be excavated by a shield excavator, and an estimation method.

Conventionally, tunnels and the like have been constructed by the soil pressure type shield method (mud soil pressure shield method). The construction environment (soil quality, water pressure, and other conditions of the ground) at the site excavated by the shield excavator changes from moment to moment depending on the excavation position at the site. For this reason, the operator manually shields the excavator while comparing the pre-planned excavation instructions with the measurement data from various measuring devices measured according to the construction environment and monitoring the measurement data. Perform the operation of.
The shield excavator will proceed with excavation according to the planned excavation instructions. The excavation instruction sheet describes the tunnel planning line showing the horizontal direction (instructed direction) and the vertical direction (instructed pitch) at the end of excavation for each ring, and excavation is performed along the tunnel planning line. It is necessary to proceed (dig). Therefore, the operator acquires the measurement direction and measurement pitch actually excavated by the shield excavator measured using a gyro compass or the like, and the difference between the instructed direction and the actually excavated direction (planned route deviation). ) Is reduced so that the digging direction of the shield excavator is controlled. The excavation direction of the shield excavator is provided behind the shield excavator and is controlled by operating a plurality of shield jacks that push the shield excavator. For example, by equalizing the propulsion amount of all shield jacks, the shield excavator goes straight. In addition, the shield excavator bends to the right by increasing the propulsion amount of the shield jack on the left side in the traveling direction as compared with the propulsion amount of the shield jack on the right side.
For example, a technique for accurately controlling the propulsion amount of a shield jack of a shield excavator even if the tunnel planning line is a curved line is disclosed (for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 7-279582

However, since the geology of the actual ground varies depending on the excavation position, for example, at a point where the geology changes, it is conceivable that the shield excavator does not go straight even if the propulsion amount of all the shield jacks is equalized. For this reason, the operator must adjust the propulsion amount of the shield jack along the tunnel planned line while monitoring the direction, pitch, and planned route deviation, and the operation is difficult unless the operator is highly skilled. ..
The number of skilled operators tends to decrease, it is difficult to secure them, and it takes a lot of time to train highly skilled operators. In addition, even a skilled operator may make a mistake in the operation timing and set values, and if the shield excavator is not operated properly, the accuracy and safety of the excavated tunnel design will decrease. There are concerns.

The present invention has been made in view of such circumstances, and an object thereof is an estimation device capable of mechanically estimating the position of a power point of a shield jack that determines the direction of excavation of a shield excavator. And to provide an estimation method.

In order to solve the above-mentioned problems, the estimation device of the embodiment of the present invention is direction data regarding the direction of excavation of the shield excavator , and includes data of any one of tail clearance, jack stroke, and jack propulsion speed. The estimation model includes a direction data acquisition unit for acquiring data and a force point position estimation unit for estimating the position of the force point to be dug by the shield excavator by inputting data including at least the direction data into the estimation model. Is a model created by executing machine learning using the training data in which the position of the force point to be dug by the shield excavator is associated with the input data including the data corresponding to the direction data. It is a feature.

Further, in the estimation device of one embodiment of the present invention, the direction data acquisition unit measures the indicated direction data instructed as the direction in which the shield excavator is digging, and the direction in which the shield excavator is actually digging. Further provided with a direction data processing unit that acquires the measured direction data and calculates the planned route deviation indicating the difference between the indicated direction data and the measurement direction data, the emphasis point estimation unit calculates the planned route deviation as the estimation model. It is characterized in that the position of the power point is estimated by inputting to.

Further, in the estimation device of the embodiment of the present invention, the direction data processing unit calculates the moving average data indicating the moving average for each predetermined time in at least one of the direction data and the planned route deviation, and said. The emphasis point position estimation unit is characterized in that the position of the emphasis point is estimated by inputting the moving average data into the estimation model.

Further, in the estimation method of one embodiment of the present invention, the direction data acquisition unit includes direction data relating to the direction of excavation of the shield excavator and includes data of any one of tail clearance, jack stroke, and jack propulsion speed. It has a step of acquiring data and a step of estimating the position of the force point to be dug by the shield excavator by inputting data including at least the direction data into the estimation model. The estimation model is a model created by executing machine learning using training data in which the position of the force point to be dug by the shield excavator is associated with the input data including the data corresponding to the direction data. It is characterized by that.

As described above, according to the present invention, it is possible to mechanically estimate the position of the force point of the shield jack that determines the direction of excavation of the shield excavator. As a result, operation support and uniform operation can be achieved, and automation of direction control of the shield excavator can be achieved by performing sufficient machine learning.

It is a schematic block diagram which shows the structural example of the shield excavator 10 applied to the estimation apparatus 30 of embodiment. It is a block diagram which shows the structural example of the estimation apparatus 30 of embodiment. It is a figure which shows the structural example of the information which the operation data storage part 34 of an embodiment stores. It is a figure which shows the structural example of the information which the direction data storage part 35 of an embodiment stores. It is a figure which shows the structural example of the information which the direction data storage part 35 of an embodiment stores. It is a flowchart which shows the operation example of the estimation apparatus 30 of embodiment.

Hereinafter, the estimation device of the embodiment will be described with reference to the drawings.

FIG. 1 is a schematic configuration diagram showing a configuration example of a shield excavator 10 to which the estimation device 30 of the present embodiment is applied. FIG. 1A shows a conceptual diagram of the shield excavator 10 viewed from the side, and FIG. 1B shows a conceptual diagram of the shield jack 20 for propelling the shield excavator 10 as viewed from the front.
As shown in FIG. 1 (a), the shield excavator 10 assembles a segment by an elector (not shown) at the rear portion of the cylindrical skin plate 11 in the negative direction of the y-axis, and performs a primary lining S. At the same time, it is a mechanism for excavating the ground. In the shield excavator 10, a chamber 12 is provided at the rear portion of the annular and face plate type cutter 16 provided with the cutter bit 15 in the negative direction of the y-axis. A plurality of soil pressure gauges D are installed on the side wall in the chamber 12. The soil pressure gauge D measures the pressure of mud in the chamber 12.
The mud-making material 14 is injected into the chamber 12 from the mud-making soil material injection pipe 13. The excavated soil deposited in the chamber 12 is kneaded by stirring with the mud soil material 14 by a kneading blade (not shown) and converted into mud.
The screw conveyor 17 discharges the mud from the chamber 12 to the conveyor 18 via the soil discharge gate G. Then, the conveyor 18 carries out the mud discharged from the screw conveyor 17 to the outside of the tunnel via the conveyor 19. The gantry M supports the screw conveyor 17, the conveyors 18, and 19.

Further, as shown in FIG. 1 (b), a plurality of shield jacks 20 are provided so as to surround the inner circumference of the skin plate 11 and are arranged between the skin plate 11 and the segment. When the shield jack 20 is propelled (extended) by hydraulic operation, the surface of the skin plate 11 is pushed and the shield excavator 10 propels.
Here, the position of the force point for propelling the surface of the skin plate 11 is set depending on which position the shield jack is propelled, and the propulsion direction of the shield excavator 10 is determined. Further, the propulsion speed of the shield excavator 10 is determined by the speed at which the shield jack 20 is propelled. That is, the propulsion direction of the shield excavator 10 is controlled by performing an operation of setting which shield jack 20 is selected. Further, the propulsion speed of the shield excavator 10 is controlled by performing an operation of setting the propulsion speed of the shield jack.

FIG. 2 is a block diagram showing a configuration example of the estimation device 30 of the embodiment.
The estimation device 30 includes an operation data acquisition unit 31, a direction data acquisition unit 32, a direction data processing unit 33, an operation data storage unit 34, a direction data storage unit 35, a learned model storage unit 36, and an emphasis position. It includes an estimation unit 37 and an estimation result output unit 38.

The operation data acquisition unit 31 acquires data on the operation performed to control the propulsion direction of the shield excavator 10. The operation data acquisition unit 31 acquires data of the operation performed on the shield jack 20 as an operation performed for controlling the propulsion direction, for example. The operation data acquisition unit 31 acquires, for example, the position of the operated shield jack 20 and the thrust of the shield jack 20, and based on the acquired operation data, determines the position of the force point in the thrust generated by all the shield jacks 20. calculate. The operation data acquisition unit 31 stores the calculated position of the emphasis point in the operation data storage unit 34.

The direction data acquisition unit 32 acquires direction data related to the propulsion direction of the shield excavator 10. As the direction data, the direction data acquisition unit 32 includes the instruction direction data related to the direction propelled by the shield excavator 10 specified in the excavation instruction sheet, and the measurement direction related to the direction actually excavated by the shield excavator 10. Get the data.

The direction data acquisition unit 32 acquires, for example, the indicated direction, the indicated pitch, and the indicated jack stroke difference as the indicated direction data.
The indicated direction is the horizontal direction (horizontal direction) specified in the excavation instruction sheet. The indicated pitch is the vertical direction (vertical direction) indicated by the excavation instruction sheet.
The designated direction and the designated pitch are, for example, designated in a ring unit in which a segment for one round of a tunnel cross section is assembled. The indicated direction indicates, for example, the horizontal direction at the point where the excavation of one ring is completed. The indicated pitch indicates, for example, the vertical orientation at the point where the excavation of one ring is completed. The direction data acquisition unit 32 stores the acquired data indicating the indicated direction, the indicated pitch, and the indicated jack stroke difference in the directional data storage unit 35.
The indicated jack stroke difference is the difference in the propulsion amount (stroke) of each of the plurality of shield jacks 20 specified in the excavation instruction sheet in order to excavate the shield excavator 10 along the curve planned by the tunnel planning line. be.
For example, when the indicated jack stroke difference is 0 (zero), the tunnel planning line is a straight line. Further, when the instruction jack stroke difference is instructed so that the propulsion amount of the shield jack 20 on the left side is larger than the propulsion amount of the shield jack 20 on the right side, the tunnel planning line is on the right side with respect to the traveling direction. It is a curved curve.

The direction data acquisition unit 32 acquires, for example, the measurement direction in the shield excavator 10 and the measurement pitch measured by using a gyro compass (not shown) provided in the shield excavator 10 as the measurement direction data. The measurement direction in the shield excavator 10 indicates a horizontal direction among the directions measured as the direction actually excavated by the shield excavator 10. The measurement pitch in the shield excavator 10 indicates a vertical direction among the directions measured as the direction actually excavated by the shield excavator 10.

Further, the direction data acquisition unit 32 acquires the distance (jack stroke) from one end to the other end of the shield jack 20 as data related to the direction actually excavated by the shield excavator 10. The direction data acquisition unit 32 acquires, for example, the jack stroke of each shield jack 20 measured by the distance measuring sensors provided in each of the shield jacks 20.

Further, the direction data acquisition unit 32 acquires the distance (tail clearance) from the inside of the skin plate 11 to the outside of the segment as data related to the direction actually excavated by the shield excavator 10. The direction data acquisition unit 32 acquires, for example, the tail clearance measured by the distance measuring sensor that measures the tail clearance.
The direction data acquisition unit 32 stores data indicating the acquired measurement direction, measurement pitch, jack stroke, and tail clearance in the direction data storage unit 35.

The direction data processing unit 33 performs various processes on the data acquired by the direction data acquisition unit 32.
The direction data processing unit 33 calculates the planned route deviation, which is the amount of deviation between the tunnel planned line and the center line of the actually dug tunnel. The direction data processing unit 33 calculates the planned route deviation in each of the horizontal direction and the vertical direction.
The direction data processing unit 33 is, for example, the length actually excavated by the shield excavator 10 from the measurement direction, the measurement pitch, and the jack stroke acquired by the direction data acquisition unit 32 in order to calculate the planned route deviation. Calculate the excavation length.

Further, the direction data processing unit 33 acquires the position of the horizontal tip of the shield excavator 10 and the position where the segment contacts the shield jack 20 (the position of the segment end) from the horizontal components of the measurement direction and the excavation length. do. Then, the direction data processing unit 33 calculates the difference between the acquired position of the tip of the shield excavator and the position on the horizontal tunnel planning line corresponding to each of the positions of the segment ends, thereby planning the horizontal direction. Calculate the route deviation. The horizontal tunnel plan line can be obtained by connecting the indicated directions for each ring in the order of ring numbers.

Further, the direction data processing unit 33 acquires the position of the tip in the vertical direction and the position of the segment end in the shield excavator 10 from the vertical components of the measurement pitch and the excavation length. Then, the direction data processing unit 33 calculates the difference between the acquired position on the tunnel planned line in the vertical direction corresponding to each position of the tip of the shield excavator and the segment end, and thereby, the deviation in the planned route in the vertical direction. Is calculated. The tunnel plan line in the vertical direction can be obtained by connecting the designated pitches for each ring in the order of ring numbers.
The direction data processing unit 33 stores the calculated horizontal and vertical planned route deviations in the direction data storage unit 35.
Further, the direction data processing unit 33 calculates the propulsion speed (jack propulsion speed) of each of the shield jacks 20 based on the time-series change of the jack stroke. The direction data processing unit 33 stores the calculated jack propulsion speed in the direction data storage unit 35.

Further, the direction data processing unit 33 moves the measurement direction data acquired by the direction data acquisition unit 32 for a short time (for example, 10 seconds) and / or for a long time (for example, 60 seconds). Is calculated. The direction data processing unit 33 stores the calculated moving average data in the direction data storage unit 35.

The trained model storage unit 36 uses data related to the propulsion direction of the shield excavator 10 as input data, and performs machine learning using the training data in which the position of the emphasis point in the propulsion direction is associated with the input data as output data. Stores an estimation model that estimates the position of the point of effort in the excavation direction, which was created by executing the data.

As the machine learning technique for creating the estimation model, any of commonly used techniques such as decision tree learning, neural network, genetic programming, and support vector machine may be used.
The learning data used for machine learning is, for example, data indicating the position of an ideal force point set by the operation of a skilled operator with respect to data related to the propulsion direction of the shield excavator. The learning data used to create the estimation model may be created using the data related to the shield excavator 10, or may be used as an image showing the situation where the mud in the chamber is discharged in a general shield machine. , The operation setting values may be associated with each other.

The estimation model is a model in which training data in which ideal emphasis positions are associated with various combinations of input data is trained, and is the same as or has been trained in a combination of input data that has already been trained. When a combination determined to be similar to the combination of input data is input, the position of the ideal emphasis point learned as the corresponding output data is output.

The emphasis point position estimation unit 37 estimates the position of the emphasis point to be set as the propulsion direction of the shield excavator 10 by using the estimation model stored in the learned model storage unit 36.
The power point position estimation unit 37 inputs a combination of data stored in the operation data storage unit 34 and the direction data storage unit 35 into the estimation model, and estimates the position of the power point output from the estimation model of the shield excavator 10. The position of the point of effort that should be set as the propulsion direction.

The estimation result output unit 38 outputs the estimation result by the emphasis point position estimation unit 37. The estimation result output unit 38 outputs the estimation result to the operation screen of the operation room (not shown) of the shield excavator 10, for example, so that the operator recognizes the estimated value of the position of the emphasis point. As a result, the operator can use the estimation device 30 as guidance. That is, the operator can select the shield jack 20 to be used based on the position of the force point estimated by the estimation device 30, and perform an operation of adjusting the thrust of the selected shield jack 20.

FIG. 3 is a diagram showing a configuration example of operation data stored by the operation data storage unit 34 of the embodiment.
As shown in FIG. 3, for example, the operation data has each item of data type, data item, and time stamp. In the data type, the type of data (either operation data, instruction direction data, measurement direction data, or moving average data) acquired from the shield excavator 10 is stored. Various data items corresponding to the data types are stored in the data items. In the time stamp, the value corresponding to the data item is stored for each time T1 to T4 .... The time stamp stores the time at predetermined time intervals (for example, every second) according to the frequency of operations.

In the example of FIG. 3, operation data indicating the actual operation is stored as a data type, and items indicating the vertical direction and the horizontal direction at the position of the emphasis point by the jack operation are stored as data items, and each time of the time stamp is stored. The position of the emphasis point acquired by the operation data acquisition unit 31 is stored.

FIG. 4 is a diagram showing a configuration example of information stored in the direction data storage unit 35 of the embodiment. FIG. 4 shows a configuration example of the instruction direction data.
As shown in FIG. 4, for example, the instruction direction data has each item of data type, data item, and ring number. The data type is stored in the data type. Various data items corresponding to the data types are stored in the data items. A value corresponding to a data item is stored in the ring number for each ring.

In the example of FIG. 4, the instruction direction data is stored as a data type, and the item indicating the instruction direction (direction with respect to the horizontal direction) and the instruction pitch (direction with respect to the vertical direction) in the direction indicated as a data item, and the instruction jack stroke. Items indicating the difference between the vertical direction and the horizontal direction are stored as the difference, and the indicated value acquired by the direction data acquisition unit 32 is stored for each ring.

FIG. 5 is a diagram showing a configuration example of information stored in the direction data storage unit 35 of the embodiment. FIG. 5 shows a configuration example of measurement direction data and moving average data.
As shown in FIG. 5, for example, the measurement direction data and the moving average data have each item of data type, data item, and time stamp. The data type is stored in the data type. Various data items corresponding to the data types are stored in the data items. In the time stamp, the value corresponding to the data item is stored for each time T1 to T4 .... As the time stamp, the time for each predetermined time according to the frequency of the operation is stored.

In the example of FIG. 5, measurement direction data or moving average data is stored as a data type, and shield excavator position (measurement direction, measurement pitch) and shield excavator tip, which are data items corresponding to the measurement direction data, are stored as data items. Each of the items of the planned route deviation (horizontal direction, vertical direction), the planned route deviation at the segment end (horizontal direction, vertical direction), the tail clearance, the jack stroke, and the jack propulsion speed is stored. Further, as the data item corresponding to the moving average data, the same item as the data item corresponding to the direction data is stored. The measurement direction data acquired by the direction data acquisition unit 32 or the moving average data calculated by the direction data processing unit 33 is stored for each time stamp.
Of the data items, for the tail clearance, instead of the measured value at predetermined time intervals, the data may be stored at predetermined time intervals at the start and end of excavation for each ring. good.

FIG. 6 is a flowchart showing an operation example of the estimation device 30 of the embodiment.
First, the operation data acquisition unit 31 of the estimation device 30 acquires operation data indicating the position of the emphasis point of the entire shield jack 20 based on the jack operation performed on the shield excavator 10 (step S10).
Next, the direction data acquisition unit 32 receives instruction direction data (instruction direction, instruction pitch, jack stroke difference) and measurement direction data (measurement direction, measurement pitch, tail clearance) as direction data regarding the direction in which the shield excavator excavates. , Jack stroke, propulsion speed) and the like (step S11). Further, the direction data processing unit 33 calculates the planned route deviation using the measurement direction data acquired by the direction data acquisition unit 32, and also calculates the measurement direction data and the moving average data of the planned route deviation.

Next, the force point position estimation unit 37 inputs the operation data and the direction data into the estimation model (step S12). The estimation model is a model that estimates and outputs output data corresponding to a combination of input data. The estimation model extracts the same or similar combination of the input data from the trained data of the estimation model for the input data combination, and associates it with the extracted data. Outputs data indicating the position of the point of effort.
Next, the power point position estimation unit 37 estimates the data output from the estimation model as the position of the power point to be propelled by the shield excavator 10 (step S13).
Then, the estimation result output unit 38 outputs the position of the power point estimated by the power point position estimation unit 37 to an operation screen or the like in the operation room (not shown) of the shield excavator 10 (step S14).

As described above, the estimation device 30 of the embodiment has a direction data acquisition unit 32 that acquires data regarding the direction of excavation of the shield excavator 10, and an estimation model (for example, trained model storage) that acquires data including at least direction data. The estimation model includes a force point position estimation unit 37 that estimates the position of the force point to be dug by the shield excavator by inputting to the estimation model) stored in the unit 36, and the estimation model is input data including data corresponding to the direction data. This is a model created by executing machine learning using the training data associated with the positions of the points of effort to be dug by the shield excavator 10.
Thereby, the estimation device 30 of the embodiment can mechanically estimate the power point of the shield jack 20 by inputting the direction data into the estimation model. Since the estimation model is a model in which the position of the force point in the excavation of the ideal shield excavator 10 is associated with the combination of the direction data, the shield jack 20 is operated as an estimated value of the position of the ideal force point. By using it, it is possible to support the operation and make the operation uniform.

Further, in the estimation device 30 of the embodiment, the direction data acquisition unit 32 actually excavates the instruction direction data (for example, the instruction direction or the instruction pitch) instructed as the direction in which the shield excavator 10 excavates, and the shield excavator 10. The measurement direction data (for example, measurement direction and measurement pitch) in which the measured direction is measured is acquired, and the direction data processing unit 33 calculates the planned route deviation which is the difference between the instruction direction data and the measurement direction data, and the point position. The estimation unit 37 estimates the position of the emphasis point by inputting the planned route deviation into the estimation model. As a result, the estimation device 30 of the embodiment can estimate the position of the emphasis point in consideration of the planned route deviation.

Further, in the estimation device 30 of the embodiment, the direction data processing unit 33 receives the direction data acquired by the direction data acquisition unit 32 or the moving average data indicating the moving average for each predetermined time in at least one of the planned route deviations. After calculation, the emphasis point position estimation unit 37 estimates the position of the emphasis point by inputting the moving average data into the estimation model. Thereby, the estimation device 30 of the embodiment can estimate the position of the emphasis point in consideration of the moving average data. For example, even if the measurement direction or measurement pitch temporarily deviates significantly from the tunnel planned line for some reason, the data of the greatly deviated part is averaged by calculating the moving average, and the deviated part is the part. It is possible to prevent the position of the biased force point from being estimated based on the data of.

Further, the estimation device 30 of the embodiment further includes an operation data acquisition unit 31 for acquiring operation data indicating an operation performed for controlling the excavation direction of the shield excavator 10, and the emphasis point position estimation unit 37 includes an operation data acquisition unit 31. By inputting the operation data into the estimation model, the position of the emphasis point is estimated. As a result, the estimation device 30 of the embodiment can estimate the position of the force point in consideration of the operation already performed on the shield excavator 10.

In the above-described embodiment, the case where the operator uses the estimation device 30 as guidance for jack operation by displaying the power point position estimated by the estimation device 30 on the operator's operation screen or the like has been described as an example. Not limited to this. The estimation device 30 estimates the position of the power point, selects the shield jack 20 to be used from the plurality of shield jacks 20 based on the estimated position of the power point, and calculates the propulsion amount of the selected shield jack 20. May be output. In this case, automatic operation may be realized by operating the shield excavator 10 based on the jack selection output by the estimation device 30 and the signal indicating the propulsion amount.

Further, in the above-described embodiment, the case where the direction data processing unit 33 calculates the planned route deviation between the position of the tip end and the position of the segment end in the shield excavator 10 has been described as an example, but the present invention is not limited to this. If the shield excavator 10 is a center-folding type excavator, the direction data processing unit 33 may calculate the planned route deviation at the center-folding point. Further, the direction data processing unit 33 may calculate the planned route deviation at the position of the rear end of the shield excavator 10 (the position of the other end different from the one end in contact with the segment in the extending portion of the shield jack 20). good.
In this case, the force point position estimation unit 37 determines the planned line deviation at the middle break point and the position of the rear end of the shield excavator 10 in addition to the planned line deviation at each position of the tip of the shield excavator 10 and the segment end. The position of the force point may be estimated by inputting to the estimation model. Further, the position of the emphasis point may be estimated by inputting only the planned line deviation at the position of the middle folding point or the rear end into the estimation model without using the planned line deviation at the tip or the segment end.

Further, in the above-described embodiment, the case where the estimation model is a model created by executing machine learning using the training data prepared in advance has been described as an example, but this estimation model is a shield excavator. The data accumulated with the excavation of 10 may be used as learning data, and learning may be accumulated (reinforcement learning is performed). By accumulating learning by the estimation model, the estimation device 30 can output a more accurate estimation result.

A computer may realize all or part of the processing performed by the estimation device 30 in the above-described embodiment. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by a computer system and executed. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. Further, the "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, and a storage device such as a hard disk built in a computer system. Further, a "computer-readable recording medium" is a communication line for transmitting a program via a network such as the Internet or a communication line such as a telephone line, and dynamically holds the program for a short period of time. It may also include a program that holds a program for a certain period of time, such as a volatile memory inside a computer system that is a server or a client in that case. Further, the above program may be for realizing a part of the above-mentioned functions, and may be further realized for realizing the above-mentioned functions in combination with a program already recorded in the computer system. It may be realized by using a programmable logic device such as FPGA.

Although the embodiment of the present invention has been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and the design and the like within a range not deviating from the gist of the present invention are also included.

10 ... Shield excavator, 20 ... Shield jack, 30 ... Estimator, 31 ... Operation data acquisition unit, 32 ... Direction data acquisition unit, 33 ... Direction data processing unit, 34 ... Operation data storage unit, 35 ... Direction data storage unit , 36 ... Learned model storage unit, 37 ... Power point position estimation unit.

Claims (4)

Direction data acquisition unit that acquires direction data including data of tail clearance, jack stroke, or jack propulsion speed, which is direction data regarding the direction of excavation of the shield excavator.
It is provided with a force point position estimation unit that estimates the position of the force point to be dug by the shield excavator by inputting data including at least the direction data into the estimation model.
The estimation model is a model created by executing machine learning using training data in which the position of the force point to be dug by the shield excavator is associated with the input data including the data corresponding to the direction data. An estimation device characterized by being. The direction data acquisition unit acquires instruction direction data instructed as the direction in which the shield excavator excavates, and measurement direction data measured as the direction in which the shield excavator actually excavates.
Further, a direction data processing unit for calculating a planned route deviation, which is a difference between the instruction direction data and the measurement direction data, is provided.
The estimation device according to claim 1, wherein the power point position estimation unit estimates the position of the power point by inputting the planned route deviation into the estimation model. The direction data processing unit calculates the moving average data indicating the moving average for each predetermined time in at least one of the direction data or the planned route deviation.
The estimation device according to claim 2, wherein the power point position estimation unit estimates the position of the power point by inputting the moving average data into the estimation model. The direction data acquisition unit acquires direction data related to the direction of excavation of the shield excavator , including data of tail clearance, jack stroke, or jack propulsion speed, and a process of acquiring direction data .
The force point position estimation unit has a step of estimating the position of the force point to be dug by the shield excavator by inputting data including at least the direction data into the estimation model.
The estimation model is a model created by executing machine learning using training data in which the position of the force point to be dug by the shield excavator is associated with the input data including the data corresponding to the direction data. An estimation method characterized by being.

Images